model:
  target: cldm.cldm.ControlLDM
  params:
    linear_start: 0.00085
    linear_end: 0.0120
    num_timesteps_cond: 1
    log_every_t: 200
    timesteps: 1000
    first_stage_key: "jpg"
    cond_stage_key: "txt"
    control_key: "hint"
    image_size: 64
    channels: 4
    cond_stage_trainable: false
    conditioning_key: crossattn
    monitor: val/loss_simple_ema
    scale_factor: 0.18215
    use_ema: False
    only_mid_control: False

    control_stage_config:
      target: cldm.cldm.ControlNet
      params:
        image_size: 32 # unused
        in_channels: 4
        hint_channels: 3
        model_channels: 320
        attention_resolutions: [4, 2, 1]
        num_res_blocks: 2
        channel_mult: [1, 2, 4, 4]
        num_heads: 8
        use_spatial_transformer: True
        transformer_depth: 1
        context_dim: 768
        use_checkpoint: True
        legacy: False

    unet_config:
      target: cldm.cldm.ControlledUnetModel
      params:
        image_size: 32 # unused
        in_channels: 4
        out_channels: 4
        model_channels: 320
        attention_resolutions: [4, 2, 1]
        num_res_blocks: 2
        channel_mult: [1, 2, 4, 4]
        num_heads: 8
        use_spatial_transformer: True
        transformer_depth: 1
        context_dim: 768
        use_checkpoint: True
        legacy: False

    first_stage_config:
      target: ldm.models.autoencoder.AutoencoderKL
      params:
        embed_dim: 4
        monitor: val/rec_loss
        ddconfig:
          double_z: true
          z_channels: 4
          resolution: 256
          in_channels: 3
          out_ch: 3
          ch: 128
          ch_mult:
            - 1
            - 2
            - 4
            - 4
          num_res_blocks: 2
          attn_resolutions: []
          dropout: 0.0
        lossconfig:
          target: torch.nn.Identity

    cond_stage_config:
      target: ldm.modules.encoders.modules.FrozenCLIPEmbedder
      params:
        _class_name: ControlNetModel
        _diffusers_version: "0.18.0.dev0"
        act_fn: silu
        attention_head_dim: 8
        block_out_channels: [320, 640, 1280, 1280]
        class_embed_type: null
        conditioning_embedding_out_channels: [16, 32, 96, 256]
        controlnet_conditioning_channel_order: rgb
        cross_attention_dim: 768
        down_block_types: ["CrossAttnDownBlock2D", "CrossAttnDownBlock2D", "CrossAttnDownBlock2D", "DownBlock2D"]
        downsample_padding: 1
        flip_sin_to_cos: true
        freq_shift: 0
        global_pool_conditions: false
        in_channels: 4
        layers_per_block: 2
        mid_block_scale_factor: 1
        norm_eps: 1e-05
        norm_num_groups: 32
        num_class_embeds: null
        only_cross_attention: false
        projection_class_embeddings_input_dim: null
        resnet_time_scale_shift: "default"
        upcast_attention: false
        use_linear_projection: false